ABSTRACT
ObjectiveIn view of the standardization of clinical diagnosis and treatment of the acute abdomen and the inheritance of diagnosis and treatment experience of prestigious veteran traditional Chinese medicine（TCM） doctors， a diagnosis and treatment reasoning algorithm based on association rule mining under incomplete evidence（AMIE）+ random walk was proposed to provide information services and technical support for primary doctors by recommending personalized diagnosis and treatment plans based on medical records. MethodThe experience of diagnosis and treatment of acute abdomen of prestigious veteran TCM doctors and the text data of clinical diagnosis and treatment guidelines of integrated TCM and western medicine were collected to complete the task of knowledge extraction and construct acute abdomen knowledge graph based on Neo4j. On the basis of ontology-supported rule-based reasoning， the rule reasoning based on similar syndromes was used to expand the syndrome combinations whose Jaccard similarity was greater than the threshold in the syndrome recommendation results. The semantic path coverage algorithm was used to calculate the semantic similarity between the symptom nodes. The symptom nodes were divided into 10 categories， and the symptom nodes in the same category were extended. The random walk algorithm was used to search the symptom nodes connected with the syndrome， and the connection rules between the syndrome and symptom nodes were extended to realize the knowledge reasoning of AMIE+ random walk. ResultThe acute abdomen knowledge graph included 1 320 nodes and 2 464 relationships. According to the link prediction evaluation index of knowledge reasoning， the reasoning results of the three algorithms in the auxiliary diagnosis and treatment of acute abdomen were compared. The AMIE+ random walk algorithm complemented the knowledge graph by extending the similar syndrome connection rules and the syndrome-symptom connection rules. Compared with the knowledge reasoning algorithm based on ontology rules， the area under the curve （AUC） was 15.18% higher and the accuracy was 30.36% higher， which achieved more accurate and effective knowledge inference. ConclusionThis study used knowledge graph technology to visualize the diagnosis and treatment of acute abdomen with TCM and western medicine， assisting primary clinicians in intuitively viewing the diagnosis and treatment process and data relationship. The proposed diagnosis and treatment reasoning algorithm can realize the personalized diagnosis and treatment plan recommendation at the level of "disease-syndrome-diagnosis-treatment-prescription"， which can assist primary doctors in disease diagnosis and treatment and clinical decision-making， contribute to the knowledge sharing and application of diagnosis and treatment experience and clinical guidelines of prestigious veteran TCM doctors， improve the level of primary clinical diagnosis and treatment， and promote the normalization and standardization of the diagnosis and treatment process of acute abdomen with integrated TCM and western medicine.
ABSTRACT
@#Knowledge graph technology has promoted the progress of new drug research and development, but domestic research starts late and domain knowledge is mostly stored in text, resulting in low rate of knowledge graph reuse.Based on multi-source and heterogeneous medical texts, this paper designed a Chinese named entity recognition model based on Bert-wwm-ext pre-training model and also integrated cascade thought, which reduced the complexity of traditional single classification and further improved the efficiency of text recognition.The experimental results showed that the model achieved the best performance with an F1-score of 0.903, a precision of 89.2%, and a recall rate of 91.5% on the self-built dataset.At the same time, the model was applied to the public dataset CCKS2019, and the results showed that the model had better performance and recognition effect.Using this model, this paper constructed a Chinese medical knowledge graph, involving 13 530 entities, 10 939 attributes and 39 247 relationships of them in total.The Chinese medical entity extraction and graph construction method proposed in this paper is expected to help researchers accelerate the new discovery of medical knowledge, and shorten the process of new drug discovery.
ABSTRACT
@#Alzheimer''s disease (AD) has brought to us huge medical and economic burdens, and so discovery of its therapeutic drugs is of great significance.In this paper, we utilized knowledge graph embedding (KGE) models to explore drug repurposing for AD on the publicly available drug repurposing knowledge graph (DRKG).Specifically, we applied four KGE models, namely TransE, DistMult, ComplEx, and RotatE, to learn the embedding vectors of entities and relations on DRKG.By using three classical knowledge graph evaluation metrics, we then evaluated and compared the performance of these models as well as the quality of the learned embedded vectors.Based on our results, we selected the RotatE model for link prediction and identified 16 drugs that might be repurposed for the treatment of AD.Previous studies have confirmed the potential therapeutic effects of 12 drugs against AD, i.e., glutathione, haloperidol, capsaicin, quercetin, estradiol, glucose, disulfire, adenosine, paroxetine, paclitaxel, glybride and amitriptyline.Our study demonstrates that drug repurposing based on KGE may provide new ideas and methods for AD drug discovery.Moreover, the RotatE model effectively integrates multi-source information of DRKG, enabling promising AD drug repurposing.The source code of this paper is available at https://github.com/LuYF-Lemon-love/AD-KGE.
ABSTRACT
To explore the research hotspots and frontier directions of pyroptosis in the field of traditional Chinese medicine(TCM), the authors searched CNKI and Web of Science for literature related to pyroptosis in TCM, screened literature according to the search strategy and inclusion criteria, and analyzed the publication trend of the included literature. VOSviewer was used to draw author cooperation and keyword co-occurrence network diagrams, and CiteSpace was employed for keyword clustering, emergence, and timeline view. Finally, 507 Chinese literature and 464 English literature were included, and it was found that the number of Chinese and English literature was increasing rapidly year by year. The co-occurrence of the authors showed that in terms of Chinese literature, there was a representative research team composed of DU Guan-hua, WANG Shou-bao and FANG Lian-hua, and for English literature, the representative research team was composed of XIAO Xiao-he, BAI Zhao-fang and XU Guang. The network visualization of Chinese and English keywords revealed that inflammation, apoptosis, oxidative stress, autophagy, organ damage, fibrosis, atherosclerosis, and ischemia-reperfusion injury were the primary research diseases and pathological processes in TCM; berberine, resveratrol, puerarin, na-ringenin, astragaloside Ⅳ, and baicalin were the representative active ingredients; NLRP3/caspase-1/GSDMD, TLR4/NF-κB/NLRP3, and p38/MAPK signaling pathways were the main research pathways. Keyword clustering, emergence, and timeline analysis indicated that the pyroptosis research in TCM focused on the mechanism of TCM monomers and compounds intervening in diseases and pathological processes. Pyroptosis is a research hotspot in the area of TCM, and the current discussion mainly focuses on the mechanism of the therapeutic effect of TCM.
Subject(s)
Pyroptosis , Medicine, Chinese Traditional , NLR Family, Pyrin Domain-Containing 3 Protein , Pattern Recognition, Automated , ApoptosisABSTRACT
ObjectiveTo construct the syndrome differentiation and treatment process in the diagnosis and treatment guideline into a visual knowledge graph using knowledge graph technology， and visualize the process from the input of clinical manifestations to the output of corresponding traditional Chinese medicine （TCM） diagnosis and prescriptions through programs， to visually display the diagnosis and treatment process as well as the data relationship for TCM practitioners. This paper facilitated the standardized and normalized TCM diagnosis and treatment of coronary heart disease， and provided technical support for the inheritance and promotion of TCM diagnosis and treatment. MethodNeo4j and py2neo were used to construct a knowledge graph based on the Guideline for Diagnosis and Treatment of Coronary Heart Disease with Stable Angina Pectoris published by China Association of Chinese Medicine Cardiovascular Disease Branch. A knowledge graph regarding the input of clinical manifestations was built through programs， visually displaying the standardized TCM diagnosis and treatment process of coronary heart disease with stable angina pectoris. ResultThe structured data were extracted from the guideline by py2neo connecting to Neo4j and imported into Neo4j to construct the knowledge graph of TCM diagnosis and treatment of coronary heart disease with stable angina pectoris， which had graph database query function. ConclusionAiming at the problems existing in the inheritance of TCM diagnosis and treatment， this paper proposed a diagnosis and treatment guideline integrating the experience of TCM experts and evidence-based evidence for coronary heart disease with stable angina pectoris， and realized the visualization process of knowledge graph based on TCM diagnosis and treatment guideline and the experience of TCM experts. It is helpful to intuitively display the whole TCM diagnosis and treatment process from symptom input to prescriptions and inherit TCM experience， providing a new paradigm for standardized and normalized TCM diagnosis and treatment.
ABSTRACT
To explore the methods of the explicitation of implicit knowledge and the construction of knowledge graph on moxibustion in medical case records of ZHOU Mei-sheng's Jiusheng. The medical case records data of Jiusheng was collected, the frequency statistic was analyzed based on Python3.8.6, complex network analysis was performed using Gephi9.2 software, community analysis was performed by the ancient and modern medical case cloud platform V2.3.5, and analysis and verification of correlation graph and weight graph were proceed by Neo4j3.5.25 image database. The disease systems with frequency≥10 % were surgery, ophthalmology and otorhinolaryngology, locomotor, digestive and respiratory systems. The diseases under the disease system were mainly carbuncle, arthritis, lumbar disc herniation and headache. The commonly used moxibustion methods were fumigating moxibustion, blowing moxibustion, direct moxibustion and warming acupuncture. The core prescription of points obtained by complex network analysis included Yatong point, Zhiyang(GV 9), Sanyinjiao(SP 6), Dazhui(GV 14), Zusanli(ST 36), Lingtai(GV 10), Xinshu(BL 15), Zhijian point and Hegu(LI 4), which were basically consistent with high-frequency points. A total of 6 communities were obtained by community analysis, corresponding to different diseases. Through the analysis of correlation graph, 13 pairs of strong association rule points were obtained. The correlation between Zhiyang(GV 9)-Dazhui(GV 14) and Yatong point-Lingtai(GV 10) was the strongest. The acupoints with high correlation with Yatong point were Zhiyang(GV 9), Lingtai(GV 10), Dazhui(GV 14), Zusanli(ST 36) and Sanyinjiao(SP 6). In the weight graph of the high-frequency disease system, the relationship of the first weight of the surgery system disease was fumigating moxibustion-carbuncle-Yatong point, and the relationship of the first weight of the ophthalmology and otorhinolaryngology system disease was blowing moxibustion-laryngitis-Hegu (LI 4). The results of correlation graph and weight graph are consistent with the results of data mining, which can be used as an effective way to study the knowledge base of moxibustion diagnosis and treatment in the future.
Subject(s)
Humans , Moxibustion , Carbuncle , Pattern Recognition, Automated , Acupuncture Therapy , Acupuncture PointsABSTRACT
Objective:To summarize the hotspots and developmental status of non-suicidal self-injury research by clustering and co-occurrence to the literature on non-suicidal self-injury on the basis of Cite Space, and in order to provide references for future research and intervention.Methods:Non-suicidal self-injury literature included in the Web of science core collection from January 1975 to August 2020 was searched, and the included literature was visualized and analyzed using Cite Space 5.5.R2 knowledge mapping software.Results:A total of 974 articles were retrieved, and the number of articles published showed an increasing trend year by year, mostly in developed countries. The country with the highest cumulative number of articles was the United States, with a total of 412 articles, and the first organization was Katholieke Univ Leuven, with a total of 42 articles. Key words co-occurrence and clustering showed that the current research focus was on adolescents, suicidal behavior, dialectical behavior therapy, and borderline personality disorder. The most cited literature was by Muehlenkamp.Conclusions:Non-suicidal self-injury research has developed rapidly in recent years. At present, non-suicidal self-injury population, related intervention measures, screening and evaluation tools, Meta-analysis and risk factor analysis are its research frontiers and hot spots.
ABSTRACT
@#Objective To map the knowledge domain of occupational health research in China. Methods Articles were searched in the China Academic Journal Network Publishing Database using“occupational health”as the subject term. Journal sources were limited to the journals of China Social Science Citation Index and core journals of China and Chinese Science Citation Database. The search period starts in 1992 and ends on November 26，2021. The valid data was visually analyzed using CiteSpace softwere. Results A total of 2 351 papers related to occupational health from 1992 to 2021 were obtained. In the past 30 years，the number of articles with the title of“occupational health”has been on the rise and reached its peak in 2014. China Occupational Medicine，Chinese Journal of Industrial Hygiene and Occupational Diseases，and Chinese Journal of Industrial Medicine were the top three journals in terms of number of articles published，which produced 438，339 and 280 articles respectively. Chinese Center for Disease Control and Prevention and Guangdong Province Hospital for Occupational Disease Prevention and Treatment were the top two organizations in terms of number of articles published，which produced 169 and 116 articles respectively. Occupational medical examination，occupational health surveillance，and occupational health risk assessment were the three hot issues in the field of occupational health research. Conclusions In the past 30 years， occupational health research in China has achieved remarkable progress in terms of article publications and interdisciplinary cooperation，and future work should focus on the academic impact of articles and interdisciplinary research cooperation.
ABSTRACT
@#Objective To map the knowledge domain of occupational health research in China. Methods Articles were searched in the China Academic Journal Network Publishing Database using“occupational health”as the subject term. Journal sources were limited to the journals of China Social Science Citation Index and core journals of China and Chinese Science Citation Database. The search period starts in 1992 and ends on November 26，2021. The valid data was visually analyzed using CiteSpace softwere. Results A total of 2 351 papers related to occupational health from 1992 to 2021 were obtained. In the past 30 years，the number of articles with the title of“occupational health”has been on the rise and reached its peak in 2014. China Occupational Medicine，Chinese Journal of Industrial Hygiene and Occupational Diseases，and Chinese Journal of Industrial Medicine were the top three journals in terms of number of articles published，which produced 438，339 and 280 articles respectively. Chinese Center for Disease Control and Prevention and Guangdong Province Hospital for Occupational Disease Prevention and Treatment were the top two organizations in terms of number of articles published，which produced 169 and 116 articles respectively. Occupational medical examination，occupational health surveillance，and occupational health risk assessment were the three hot issues in the field of occupational health research. Conclusions In the past 30 years， occupational health research in China has achieved remarkable progress in terms of article publications and interdisciplinary cooperation，and future work should focus on the academic impact of articles and interdisciplinary research cooperation.
ABSTRACT
Objective@#To establish the knowledge graph of “disease-syndrome-symptom-method-formula” in Treatise on Febrile Diseases (Shang Han Lun,《伤寒论》) for reducing the fuzziness and uncertainty of data, and for laying a foundation for later knowledge reasoning and its application.@*Methods@#Under the guidance of experts in the classical formula of traditional Chinese medicine (TCM), the method of “top-down as the main, bottom-up as the auxiliary” was adopted to carry out knowledge extraction, knowledge fusion, and knowledge storage from the five aspects of the disease, syndrome, symptom, method, and formula for the original text of Treatise on Febrile Diseases, and so the knowledge graph of Treatise on Febrile Diseases was constructed. On this basis, the knowledge structure query and the knowledge relevance query were realized in a visual manner. @*Results@#The knowledge graph of “disease-syndrome-symptom-method-formula” in the Treatise on Febrile Diseases was constructed, containing 6 469 entities and 10 911 relational triples, on which the query of entities and their relationships can be carried out and the query result can be visualized. @*Conclusion@#The knowledge graph of Treatise on Febrile Diseases systematically realizes its digitization of the knowledge system, and improves the completeness and accuracy of the knowledge representation, and the connection between “disease-syndrome-symptom-treatment-formula”, which is conducive to the sharing and reuse of knowledge can be obtained in a clear and efficient way.
ABSTRACT
@#With the widespread use of Internet, the amount of data in the field of traditional Chinese medicine (TCM) is growing exponentially. Consequently, there is much attention on the collection of useful knowledge as well as its effective organization and expression. Knowledge graphs have thus emerged, and knowledge reasoning based on this tool has become one of the hot spots of research. This paper first presents a brief introduction to the development of knowledge graphs and knowledge reasoning, and explores the significance of knowledge reasoning. Secondly, the mainstream knowledge reasoning methods, including knowledge reasoning based on traditional rules, knowledge reasoning based on distributed feature representation, and knowledge reasoning based on neural networks are introduced. Then, using stroke as an example, the knowledge reasoning methods are expounded, the principles and characteristics of commonly used knowledge reasoning methods are summarized, and the research and applications of knowledge reasoning techniques in TCM in recent years are sorted out. Finally, we summarize the problems faced in the development of knowledge reasoning in TCM, and put forward the importance of constructing a knowledge reasoning model suitable for the field of TCM.
ABSTRACT
El control de la propagación de las enfermedades infecciosas requiere investigaciones epidemiológicas exhaustivas, lo que ha quedado validado con el desempeño del Ministerio de Salud Pública a lo largo de varias décadas en el combate a numerosas enfermedades como el dengue, el cólera y varios tipos de influenza, entre otras. Sin embargo, la pandemia COVID-19 está poniendo a prueba los más rigurosos protocolos epidemiológicos de Cuba y del mundo por su elevada capacidad de contagio y propagación. Ante este contexto, el presente artículo se propuso emplear los grafos de conocimiento para el apoyo a los estudios epidemiológicos de la COVID-19, haciendo mayor énfasis en los factores de exposición y rastreo de los contactos. Para alcanzar este objetivo se realizó un estudio relacionado con el estado del arte sobre grafos de conocimiento y su empleo en el sector de la salud, particularmente en la lucha contra el nuevo coronavirus SARS-CoV-2. La investigación tuvo como soporte un enfoque metodológico de creación y uso de grafos de conocimiento adaptado al campo de estudio. Los resultados se simulan en el escenario del brote producido a mediados del mes de julio del año 2020 en el municipio de Bauta de la provincia de Artemisa, empleando para esto datos de la realidad, extraídos de la Web, combinados con otros datos simulados(AU)
Control of the spread of infectious diseases requires exhaustive epidemiological research, as has been validated by the performance of the Ministry of Public Health during several decades of combat against numerous diseases, such as dengue, cholera and various types of influenza, among others. However, the COVID-19 pandemic is testing the limits of the most rigorous epidemiological protocols in Cuba and worldwide, due to its high transmissibility and fast spread. In this context, the present study had the purpose of using knowledge graphs to support epidemiological research about COVID-19, with greater emphasis on exposure factors and contact tracing. To achieve this end, a study was conducted about the state of the art of knowledge graphs and their use in the health care sector, particularly in the combat against the novel coronavirus SARS-CoV-2. The research applied a methodological approach based on the development and use of knowledge graphs adjusted to the study field. Results are simulated in the context of the outbreak occurring in mid July 2020 in the municipality of Bauta, Artemisa province, using real data obtained from the Internet and combined with other simulated data(AU)
Subject(s)
Humans , Male , Female , Coronavirus Infections/epidemiology , COVID-19/diagnosis , COVID-19/prevention & control , COVID-19/therapyABSTRACT
The construction of medical knowledge platform is a core value of the intelligent construction of electronic medical records. The hospital-wide knowledge base construction covers a wide range of content, including multiple healthcare scenarios such as medicine, testing, inspection, surgery, blood transfusion and nursing. This article introduced how Jiangsu Province People′s Hospital used knowledge graphs and rule engine to construct a hospital knowledge management platform, realize the integration of knowledge-based knowledge base and a non-knowledge-based knowledge base, and embed clinical diagnosis and treatment rules into the information system for different flexible application scenarios.Finally, a multi-dimensional knowledge base was formed to realize the unified knowledge information integration of various clinical expert knowledge, and to provide integrated display and decision support for all departments, as well as realizing real-time data verification, prompting and control in each link.
ABSTRACT
Objective:To analyze the knowledge graph of the papers published in the core journals of emergency medicine from 2015 to 2019, to present the overall situation of the research in the field of emergency medicine, to highlight the important contents in the research progress, and to unearth the research hotspots reported in the journals of emergency medicine.Methods:The relevant literatures of 7 core journals of emergency medicine were retrieved and exported from CNKI and Wanfang databases published in 2015-2019. A total of 7753 valid literatures were included. The visualization software CiteSpace was used to analyze the information of authors, institutions and keywords in the exported literatures to generate visual graphs.Results:By analyzing the knowledge graph from 2015 to 2019, it is found that Yu Xuezhong, Zhu Huadong, Zhang Jinsong, Zhang Mao, Liu Xinwei, Liu Yin, Xu Jun, and Nie Sinnan were the backbone of the author group in the field of emergency medicine. Emergency Department of Peking Union Medical College Hospital, Beijing Chaoyang Hospital Affiliated to Capital Medical University, Emergency Department of PLA General Hospital, Emergency Medicine Department of Eastern Theater General Hospital, Emergency Department of Xijing Hospital, and Emergency Medicine Department of Shenyang Military Region General Hospital were the institutions with the most publications. In recent 5 years, the core journals of emergency medicine focused on the topics on mortality, acute lung injury, cardiac arrest, prognosis, mechanical ventilation, acute myocardial infarction and hemoperfusion.Conclusions:The visual graphs generated by CiteSpace helps to intuitively understand the critical path, development trend and frontier hot spots of the evolution of the research field of emergency medicine, and provides more basis for future related research.
ABSTRACT
The medical literature contains a wealth of valuable medical knowledge. At present, the research on extraction of entity relationship in medical literature has made great progress, but with the exponential increase in the number of medical literature, the annotation of medical text has become a big problem. In order to solve the problem of manual annotation time such as consuming and heavy workload, a remote monitoring annotation method is proposed, but this method will introduce a lot of noise. In this paper, a novel neural network structure based on convolutional neural network is proposed, which can solve a large number of noise problems. The model can use the multi-window convolutional neural network to automatically extract sentence features. After the sentence vectors are obtained, the sentences that are effective to the real relationship are selected through the attention mechanism. In particular, an entity type (ET) embedding method is proposed for relationship classification by adding entity type characteristics. The attention mechanism at sentence level is proposed for relation extraction in allusion to the unavoidable labeling errors in training texts. We conducted an experiment using 968 medical references on diabetes, and the results showed that compared with the baseline model, the present model achieved good results in the medical literature, and F1-score reached 93.15%. Finally, the extracted 11 types of relationships were stored as triples, and these triples were used to create a medical map of complex relationships with 33 347 nodes and 43 686 relationship edges. Experimental results show that the algorithm used in this paper is superior to the optimal reference system for relationship extraction.
Subject(s)
Humans , Algorithms , China , Diabetes Mellitus , Electronic Health Records , Neural Networks, ComputerABSTRACT
The paper retrieves the Electronic Medical Records (EMR) literatures from the journals included in A Guide to the Core Journals of China and Citation Report of Chinese Sci-tech periodicals (core board) from 2012-2016,carries out bibliometric analysis from the aspects of time,source journals,citation status,high frequency keywords and so on,so as to obtain the study status and tendency of EMR in recent years.
ABSTRACT
As the new development of scientometrics and informetrics, knowledge graph has infiltrated into the financial, industrial and medical fields, and become a hot issue in the real world research. In this article, the concept and features of knowledge graph, construction and the existing softwares, the application status and development prospect in the TCM field were reviewed, which may provide references for research on the knowledge graph in the TCM field.
ABSTRACT
ObjectiveTo assess China’s newly evolved hot spots and novelty of structural electronic medical record in TCM field.Methods Articles about electronic medical record in TCM field were retrieved from CNKI from January 2000 to December 2015, focusing on researchers, research institutes, and key words for bibliometric analysis. Then visualization software CiteSpace was used to establish co-occurrence network.ResultsThe top 3 productive authors were LIU Bao-yan (13 articles), ZHANG Run-shun (8 articles), XIE Qi (7 articles), and ZHOU Xue-zhong (7 articles). Institutes highly cooperated with others included China Academy of Chinese Medical Sciences, Information Engineering College of Hubei University of Chinese Medicine and The First Affiliated Hospital of Henan University of Chinese Medicine. The major clusters were TCM diagnosis (#0), China’s TCM information (#1), artificial intelligence (#2), medical record management (#3), and medical laboratory department (#4). The representative keywords involved electronic medical record, TCM hospital, data mining, telemedicine, and artificial intelligence. ConclusionIn the field of TCM electronic medical record, cooperation is not sufficiently facilitated among researchers and institutes. Research hot spots are not formed and novelty is not obvious, which is probably because of the overall status quo for China’s TCM information construction.
ABSTRACT
Objective To discuss the use of knowledge graph technology to connect various trivial and fragmented knowledge in various medical information systems and support comprehensive knowledge retrieval and intelligent medical applications such as Q & A and clinical decision support.Methods Based on the construction of medical field ontology and semantic labeling of medical knowledge base,the medical knowledge graph was constructed and applied to intelligent medicine,with chronic disease taken as an example.Results The construction method of medical knowledge graph and its application in semantic analysis,reasoning and disease-assisted diagnosis system based on medical knowledge base were put forward.Conclusion The application of intelligent medicine based on knowledge graph will play an important role in contradiction between the supply of high-quality medical resources and increasing medical requirements.
ABSTRACT
A semantic predication network was developed by processing the documents on schizophrenia into se-mantic predication sets using SemRep, from which the core information was extracted to produce a graphic summary which was consisted of highly cohesive cliques.The automatic methods for summarizing biomedical documents were studied using the network properties combined with semantic information.The subthemes in the summary obtained by clustering were evaluated according to the clique co-node matrix and the contents of the summary were assessed according to the reference criteria.The accuracy was 0.93, the recall was 0.68, and the F-value was 0.79 for the summary, indicating that this method can effectively recognize the core information in documents and the semantic information in network graphics.